© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 60578
    Prev
    Next
    INDEX
    Explanations

    directory, volume, framed, satisfied

    np_acts-logits-general · gemini-2.5-flash-lite

    solution, great, alpine, experience, text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uação
    0.48
    ümü
    0.47
    ()}
    0.44
     працю
    0.44
    clr
    0.43
    INTRODUCTION
    0.43
    後は
    0.42
    іл
    0.41
    何を
    0.41
    %\
    0.41
    POSITIVE LOGITS
    speech
    0.53
    ක
    0.51
    symbols
    0.50
    search
    0.46
    ات
    0.46
    मय
    0.45
    mash
    0.44
     Wend
    0.44
    sports
    0.44
    شت
    0.43
    Activations Density 0.000%

    No Known Activations